Data complexity meta-features for regression problems

Data complexity meta-features for regression problems

Author Lorena, Ana C. Autor UNIFESP Google Scholar
Maciel, Aron I. Autor UNIFESP Google Scholar
de Miranda, Pericles B. C. Google Scholar
Costa, Ivan G. Google Scholar
Prudencio, Ricardo B. C. Google Scholar
Abstract In meta-learning, classification problems can be described by a variety of features, including complexity measures. These measures allow capturing the complexity of the frontier that separates the classes. For regression problems, on the other hand, there is a lack of such type of measures. This paper presents and analyses measures devoted to estimate the complexity of the function that should fitted to the data in regression problems. As case studies, they are employed as meta-features in three meta-learning setups: (i) the first one predicts the regression function type of some synthetic datasets; (ii) the second one is designed to tune the parameter values of support vector regressors; and (iii) the third one aims to predict the performance of various regressors for a given dataset. The results show the suitability of the new measures to describe the regression datasets and their utility in the meta-learning tasks considered. In cases (ii) and (iii) the achieved results are also similar or better than those obtained by the use of classical meta-features in meta-learning.
Keywords Meta-learning
Complexity measures
xmlui.dri2xhtml.METS-1.0.item-coverage Dordrecht
Language English
Sponsor FAPESP
IZKF Aachen
Grant number FAPESP: 2012/22608-8
CNPq: 482222/2013-1
CNPq: 308858/2014-0
CNPq: 305611/2015-1
Date 2018
Published in Machine Learning. Dordrecht, v. 107, n. 1, p. 209-246, 2018.
ISSN 0885-6125 (Sherpa/Romeo, impact factor)
Publisher Springer
Extent 209-246
Access rights Closed access
Type Article
Web of Science ID WOS:000419684700008

Show full item record


File Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)




My Account